What are the dependencies and runtime requirements?
Requires Elixir and either a Phoenix application or a Plug application with Bandit. The library depends on `:mime`, `:mcp_sse`, and optionally `:plug` and `:bandit`.
@kEND
基本情報
An elixir Model Context Protocal (MCP) server library which uses the Server-Sent Events (SSE) transport type
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"mcp_sse": {
"command": "npx",
"args": [
"@modelcontextprotocol/inspector@latest"
],
"env": {
"MCP_SERVER_URL": "localhost:4000"
}
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
MCP over SSE is an Elixir library that provides a simple implementation of the Model Context Protocol (MCP) using Server-Sent Events. It is intended for developers building MCP servers with Phoenix or Plug/Bandit applications.
Add the library as a dependency, configure MIME types and the MCP server module, implement the MCPServer behaviour, and set up routing for the /sse and /message endpoints. Run your application with mix phx.server or mix run --no-halt. Connect clients such as MCP Inspector or Cursor to the SSE endpoint.
Requires Elixir and either a Phoenix application or a Plug application with Bandit. The library depends on `:mime`, `:mcp_sse`, and optionally `:plug` and `:bandit`.
Each connection must have a session ID. If the client does not provide one, the server automatically generates a new session ID and attaches it to query parameters for both the SSE and message endpoints.
It uses Server-Sent Events (SSE) for server-to-client messages and HTTP POST for client-to-server JSON-RPC requests, both over configurable paths.
Yes. You can configure `sse_path`, `message_path`, and `sse_keepalive_timeout` (in milliseconds) in your application config. Setting the timeout to `:infinity` disables keepalive pings.
Responses must follow the MCP specification. Supported content types are `text`, `image`, and `resource`. For structured data, convert it to a formatted JSON string using a JSON encoder.

Model Context Protocol Servers
Hindsight: Agent Memory That Learns

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep
コメント